© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10444
    Prev
    Next
    INDEX
    Explanations

    centuries, generations, editions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ه
    4.24
    a
    3.90
    o
    3.80
    i
    3.55
    en
    3.44
    ി
    3.29
    м
    3.25
    া
    3.08
    ي
    2.96
    에
    2.84
    POSITIVE LOGITS
    ঙ্কর
    2.36
     AIAA
    2.27
    ಞ
    2.23
    ,~
    2.23
     numpy
    2.22
     แชร์
    2.21
     程
    2.19
    сква
    2.17
    deserialize
    2.16
     ofApp
    2.16
    Activations Density 0.052%

    No Known Activations